Updated from Linux LTS 3.10.25 to 3.10.26

fs/ceph/addr.c

@@ -213,9 +213,13 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 	if (err < 0) {
 		SetPageError(page);
 		goto out;
-	} else if (err < PAGE_CACHE_SIZE) {
+	} else {
+		if (err < PAGE_CACHE_SIZE) {
 		/* zero fill remainder of page */
-		zero_user_segment(page, err, PAGE_CACHE_SIZE);
+			zero_user_segment(page, err, PAGE_CACHE_SIZE);
+		} else {
+			flush_dcache_page(page);
+		}
 	}
 	SetPageUptodate(page);
 

fs/ceph/file.c

@@ -313,9 +313,9 @@ static int striped_read(struct inode *inode,
 {
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	u64 pos, this_len;
+	u64 pos, this_len, left;
 	int io_align, page_align;
-	int left, pages_left;
+	int pages_left;
 	int read;
 	struct page **page_pos;
 	int ret;
@@ -346,47 +346,40 @@ more:
 		ret = 0;
 	hit_stripe = this_len < left;
 	was_short = ret >= 0 && ret < this_len;
-	dout("striped_read %llu~%u (read %u) got %d%s%s\n", pos, left, read,
+	dout("striped_read %llu~%llu (read %u) got %d%s%s\n", pos, left, read,
 	     ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
 
-	if (ret > 0) {
-		int didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
-
-		if (read < pos - off) {
-			dout(" zero gap %llu to %llu\n", off + read, pos);
-			ceph_zero_page_vector_range(page_align + read,
-						    pos - off - read, pages);
+	if (ret >= 0) {
+		int didpages;
+		if (was_short && (pos + ret < inode->i_size)) {
+			u64 tmp = min(this_len - ret,
+					inode->i_size - pos - ret);
+			dout(" zero gap %llu to %llu\n",
+				pos + ret, pos + ret + tmp);
+			ceph_zero_page_vector_range(page_align + read + ret,
+							tmp, pages);
+			ret += tmp;
 		}
+
+		didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
 		pos += ret;
 		read = pos - off;
 		left -= ret;
 		page_pos += didpages;
 		pages_left -= didpages;
 
-		/* hit stripe? */
-		if (left && hit_stripe)
+		/* hit stripe and need continue*/
+		if (left && hit_stripe && pos < inode->i_size)
 			goto more;
 	}
 
-	if (was_short) {
+	if (read > 0) {
+		ret = read;
 		/* did we bounce off eof? */
 		if (pos + left > inode->i_size)
 			*checkeof = 1;
-
-		/* zero trailing bytes (inside i_size) */
-		if (left > 0 && pos < inode->i_size) {
-			if (pos + left > inode->i_size)
-				left = inode->i_size - pos;
-
-			dout("zero tail %d\n", left);
-			ceph_zero_page_vector_range(page_align + read, left,
-						    pages);
-			read += left;
-		}
 	}
 
-	if (ret >= 0)
-		ret = read;
 	dout("striped_read returns %d\n", ret);
 	return ret;
 }
@@ -618,6 +611,8 @@ out:
 		if (check_caps)
 			ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY,
 					NULL);
+	} else if (ret != -EOLDSNAPC && written > 0) {
+		ret = written;
 	}
 	return ret;
 }

fs/ceph/ioctl.c

@@ -211,8 +211,12 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
 	snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
 		 ceph_ino(inode), dl.object_no);
 
-	ceph_calc_ceph_pg(&pgid, dl.object_name, osdc->osdmap,
-		ceph_file_layout_pg_pool(ci->i_layout));
+	r = ceph_calc_ceph_pg(&pgid, dl.object_name, osdc->osdmap,
+				ceph_file_layout_pg_pool(ci->i_layout));
+	if (r < 0) {
+		up_read(&osdc->map_sem);
+		return r;
+	}
 
 	dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid);
 	if (dl.osd >= 0) {

fs/ceph/mds_client.c

@@ -414,6 +414,9 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 {
 	struct ceph_mds_session *s;
 
+	if (mds >= mdsc->mdsmap->m_max_mds)
+		return ERR_PTR(-EINVAL);
+
 	s = kzalloc(sizeof(*s), GFP_NOFS);
 	if (!s)
 		return ERR_PTR(-ENOMEM);
@@ -639,6 +642,8 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
 		req->r_unsafe_dir = NULL;
 	}
 
+	complete_all(&req->r_safe_completion);
+
 	ceph_mdsc_put_request(req);
 }
 
@@ -1840,8 +1845,11 @@ static int __do_request(struct ceph_mds_client *mdsc,
 	int mds = -1;
 	int err = -EAGAIN;
 
-	if (req->r_err || req->r_got_result)
+	if (req->r_err || req->r_got_result) {
+		if (req->r_aborted)
+			__unregister_request(mdsc, req);
 		goto out;
+	}
 
 	if (req->r_timeout &&
 	    time_after_eq(jiffies, req->r_started + req->r_timeout)) {
@@ -2151,7 +2159,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	if (head->safe) {
 		req->r_got_safe = true;
 		__unregister_request(mdsc, req);
-		complete_all(&req->r_safe_completion);
 
 		if (req->r_got_unsafe) {
 			/*
@@ -3040,8 +3047,10 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
 	fsc->mdsc = mdsc;
 	mutex_init(&mdsc->mutex);
 	mdsc->mdsmap = kzalloc(sizeof(*mdsc->mdsmap), GFP_NOFS);
-	if (mdsc->mdsmap == NULL)
+	if (mdsc->mdsmap == NULL) {
+		kfree(mdsc);
 		return -ENOMEM;
+	}
 
 	init_completion(&mdsc->safe_umount_waiters);
 	init_waitqueue_head(&mdsc->session_close_wq);

fs/ceph/mdsmap.c

@@ -138,6 +138,8 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 				m->m_info[mds].export_targets =
 					kcalloc(num_export_targets, sizeof(u32),
 						GFP_NOFS);
+				if (m->m_info[mds].export_targets == NULL)
+					goto badmem;
 				for (j = 0; j < num_export_targets; j++)
 					m->m_info[mds].export_targets[j] =
 					       ceph_decode_32(&pexport_targets);
@@ -170,7 +172,7 @@ bad:
 		       DUMP_PREFIX_OFFSET, 16, 1,
 		       start, end - start, true);
 	ceph_mdsmap_destroy(m);
-	return ERR_PTR(-EINVAL);
+	return ERR_PTR(err);
 }
 
 void ceph_mdsmap_destroy(struct ceph_mdsmap *m)

fs/ceph/super.c

@@ -357,7 +357,7 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
 	}
 	err = -EINVAL;
 	dev_name_end--;		/* back up to ':' separator */
-	if (*dev_name_end != ':') {
+	if (dev_name_end < dev_name || *dev_name_end != ':') {
 		pr_err("device name is missing path (no : separator in %s)\n",
 				dev_name);
 		goto out;

fs/gfs2/aops.c

@@ -999,6 +999,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	struct address_space *mapping = inode->i_mapping;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
 	int rv;
@@ -1019,6 +1020,35 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 	if (rv != 1)
 		goto out; /* dio not valid, fall back to buffered i/o */
 
+	/*
+	 * Now since we are holding a deferred (CW) lock at this point, you
+	 * might be wondering why this is ever needed. There is a case however
+	 * where we've granted a deferred local lock against a cached exclusive
+	 * glock. That is ok provided all granted local locks are deferred, but
+	 * it also means that it is possible to encounter pages which are
+	 * cached and possibly also mapped. So here we check for that and sort
+	 * them out ahead of the dio. The glock state machine will take care of
+	 * everything else.
+	 *
+	 * If in fact the cached glock state (gl->gl_state) is deferred (CW) in
+	 * the first place, mapping->nr_pages will always be zero.
+	 */
+	if (mapping->nrpages) {
+		loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
+		loff_t len = iov_length(iov, nr_segs);
+		loff_t end = PAGE_ALIGN(offset + len) - 1;
+
+		rv = 0;
+		if (len == 0)
+			goto out;
+		if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+			unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
+		rv = filemap_write_and_wait_range(mapping, lstart, end);
+		if (rv)
+			return rv;
+		truncate_inode_pages_range(mapping, lstart, end);
+	}
+
 	rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
 				  offset, nr_segs, gfs2_get_block_direct,
 				  NULL, NULL, 0);

fs/gfs2/ops_fstype.c

@@ -1317,8 +1317,18 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 	if (IS_ERR(s))
 		goto error_bdev;
 
-	if (s->s_root)
+	if (s->s_root) {
+		/*
+		 * s_umount nests inside bd_mutex during
+		 * __invalidate_device().  blkdev_put() acquires
+		 * bd_mutex and can't be called under s_umount.  Drop
+		 * s_umount temporarily.  This is safe as we're
+		 * holding an active reference.
+		 */
+		up_write(&s->s_umount);
 		blkdev_put(bdev, mode);
+		down_write(&s->s_umount);
+	}
 
 	memset(&args, 0, sizeof(args));
 	args.ar_quota = GFS2_QUOTA_DEFAULT;